no code implementations • 11 Apr 2024 • Xavier Alameda-Pineda, Angus Addlesee, Daniel Hernández García, Chris Reinke, Soraya Arias, Federica Arrigoni, Alex Auternaud, Lauriane Blavette, Cigdem Beyan, Luis Gomez Camara, Ohad Cohen, Alessandro Conti, Sébastien Dacunha, Christian Dondrup, Yoav Ellinson, Francesco Ferro, Sharon Gannot, Florian Gras, Nancie Gunson, Radu Horaud, Moreno D'Incà, Imad Kimouche, Séverin Lemaignan, Oliver Lemon, Cyril Liotard, Luca Marchionni, Mordehay Moradi, Tomas Pajdla, Maribel Pino, Michal Polic, Matthieu Py, Ariel Rado, Bin Ren, Elisa Ricci, Anne-Sophie Rigaud, Paolo Rota, Marta Romeo, Nicu Sebe, Weronika Sieińska, Pinchas Tandeitnik, Francesco Tonini, Nicolas Turro, Timothée Wintz, Yanchao Yu
Despite the many recent achievements in developing and deploying social robotics, there are still many underexplored environments and applications for which systematic evaluation of such systems by end-users is necessary.
no code implementations • 21 Nov 2023 • Radu Horaud, Humberto Sossa
In this paper we address the problem of recognizing 3-D polyhedral objects from 2-D images by indexing.
no code implementations • 21 Nov 2023 • Radu Horaud, Fadi Dornaika
In the light of this comparison, the non-linear optimization method, that solves for rotation and translation simultaneously, seems to be the most robust one with respect to noise and to measurement errors.
no code implementations • 21 Nov 2023 • Radu Horaud, Fadi Dornaika, Bernard Espiau
In this paper we present a visual servoing approach to the problem of object grasping and more generally, to the problem of aligning an end-effector with an object.
no code implementations • 20 Nov 2023 • Nicolas Andreff, Radu Horaud, Bernard Espiau
In this paper we propose a new flexible method for hand-eye calibration.
no code implementations • 6 Apr 2022 • Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda
The method alternates between the estimation of (i)~the rigid transformation (scale, rotation, and translation) and (ii)~the non-rigid deformation between an arbitrarily-viewed face and a face model.
no code implementations • 1 Feb 2022 • Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda, Jacob Donley, Anurag Kumar
This paper investigates the impact of head movements on audio-visual speech enhancement (AVSE).
no code implementations • 30 Jul 2021 • Vineet Gandhi, Jan Cech, Radu Horaud
Most of these systems suffer from the problems of noise in the range-data and resolution mismatch between the range sensor and the color cameras, since the resolution of current range sensors is much less than the resolution of color cameras.
no code implementations • 21 Jun 2021 • Avinash Sharma, Radu Horaud, Diana Mateus
We discuss solutions for the exact and inexact graph isomorphism problems and recall the main spectral properties of the combinatorial graph Laplacian; We provide a novel analysis of the commute-time embedding that allows us to interpret the latter in terms of the PCA of a graph, and to select the appropriate dimension of the associated embedded metric space; We derive a unit hyper-sphere normalization for the commute-time embedding that allows us to register two shapes with different samplings; We propose a novel method to find the eigenvalue-eigenvector ordering and the eigenvector signs using the eigensignature (histogram) which is invariant to the isometric shape deformations and fits well in the spectral graph matching framework, and we present a probabilistic shape matching formulation using an expectation maximization point registration algorithm which alternates between aligning the eigenbases and finding a vertex-to-vertex assignment.
no code implementations • 15 Dec 2020 • Andrei Zaharescu, Radu Horaud
In this paper we address the problem of building a class of robust factorization algorithms that solve for the shape and motion parameters with both affine (weak perspective) and perspective camera models.
no code implementations • 14 Dec 2020 • Diana Mateus, Radu Horaud, David Knossow, Fabio Cuzzolin, Edmond Boyer
Matching articulated shapes represented by voxel-sets reduces to maximal sub-graph isomorphism when each set is described by a weighted graph.
no code implementations • 12 Dec 2020 • Georgios D. Evangelidis, Miles Hansard, Radu Horaud
The accuracy of the method is not compromised, owing to three properties of the data-term in the energy function.
no code implementations • 12 Dec 2020 • Radu Horaud, Miles Hansard, Georgios Evangelidis, Clement Menier
Time-of-flight (TOF) cameras are sensors that can measure the depths of scene-points, by illuminating the scene with a controlled laser or LED source, and then analyzing the reflected light.
no code implementations • 11 Dec 2020 • Miles Hansard, Radu Horaud
The recovery of visual direction and depth from retinal images is discussed, with reference to the relevant psychophysical and neurophysiological literature.
no code implementations • 10 Dec 2020 • Yves Dufournaud, Cordelia Schmid, Radu Horaud
In this paper we address the problem of matching two images with two different resolutions: a high-resolution image and a low-resolution one.
no code implementations • 10 Dec 2020 • Andrei Zaharescu, Edmond Boyer, Radu Horaud
However, explicit mesh representations, while allowing for accurate surface modelling, suffer from the inherent difficulty of reliably dealing with self-intersections and topological changes such as merges and splits.
no code implementations • 9 Dec 2020 • Miles Hansard, Radu Horaud
Gabor functions can also be combined in an `energy model' of the complex cell response.
no code implementations • 9 Dec 2020 • Vasil Khalidov, Florence Forbes, Radu Horaud
The algorithm and its variants are tested and evaluated within the task of 3D localization of several speakers using both auditory and visual data.
no code implementations • 9 Dec 2020 • Radu Horaud, Florence Forbes, Manuel Yguel, Guillaume Dewaele, Jian Zhang
This paper addresses the issue of matching rigid and articulated shapes through probabilistic point registration.
no code implementations • 8 Dec 2020 • Radu Horaud, Matti Niskanen, Guillaume Dewaele, Edmond Boyer
We address the problem of human motion tracking by registering a surface to 3-D data.
6 code implementations • 29 Oct 2020 • Xiang Hao, Xiangdong Su, Radu Horaud, Xiaofei Li
In our proposed FullSubNet, we connect a pure full-band model and a pure sub-band model sequentially and use practical joint training to integrate these two types of models' advantages.
no code implementations • 26 Oct 2020 • Zhiqi Kang, Mostafa Sadeghi, Radu Horaud
We propose to model inliers and outliers with the generalized Student's t-probability distribution function, a heavy-tailed distribution that is immune to non-Gaussian errors in the data.
no code implementations • 23 Sep 2020 • Sylvain Guy, Stéphane Lathuilière, Pablo Mesejo, Radu Horaud
Visual voice activity detection (V-VAD) uses visual features to predict whether a person is speaking or not.
no code implementations • 2 Jun 2020 • Xavier Alameda-Pineda, Vincent Drouard, Radu Horaud
In this paper, we propose a variational approximation of piecewise linear dynamical systems.
no code implementations • 14 Apr 2020 • Mostafa Sadeghi, Xavier Alameda-Pineda, Radu Horaud
The results show that the proposed analysis is consistent with supervised metrics and that it can be used to measure the accuracy of both predicted landmarks and of automatically annotated 3DFA datasets, to detect errors and to eliminate them.
no code implementations • 24 Oct 2019 • Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud
This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE).
no code implementations • 7 Aug 2019 • Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud
Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data.
2 code implementations • CVPR 2020 • Yihong Xu, Aljosa Osep, Yutong Ban, Radu Horaud, Laura Leal-Taixe, Xavier Alameda-Pineda
In this paper, we bridge this gap by proposing a differentiable proxy of MOTA and MOTP, which we combine in a loss function suitable for end-to-end training of deep multi-object trackers.
Ranked #4 on Multi-Object Tracking on 2D MOT 2015
no code implementations • 2 Apr 2019 • Guillaume Delorme, Yihong Xu, Stephane Lathuilière, Radu Horaud, Xavier Alameda-Pineda
Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training.
no code implementations • 28 Feb 2019 • Benoit Massé, Stéphane Lathuilière, Pablo Mesejo, Radu Horaud
In this paper we address the problems of detecting objects of interest in a video and of estimating their locations, solely from the gaze directions of people present in the video.
no code implementations • 8 Feb 2019 • Simon Leglaive, Umut Simsekli, Antoine Liutkus, Laurent Girin, Radu Horaud
This paper focuses on single-channel semi-supervised speech enhancement.
1 code implementation • 5 Feb 2019 • Simon Leglaive, Laurent Girin, Radu Horaud
In this paper we address the problem of enhancing speech signals in noisy mixtures using a source separation approach.
no code implementations • 16 Nov 2018 • Simon Leglaive, Laurent Girin, Radu Horaud
In this paper we address speaker-independent multichannel speech enhancement in unknown noisy environments.
no code implementations • 28 Sep 2018 • Yutong Ban, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud
We propose a variational inference model which amounts to approximate the joint distribution with a factorized distribution.
no code implementations • ECCV 2018 • Stéphane Lathuilière, Pablo Mesejo, Xavier Alameda-Pineda, Radu Horaud
In this paper, we address the problem of how to robustly train a ConvNet for regression, or deep robust regression.
2 code implementations • 22 Mar 2018 • Stéphane Lathuilière, Pablo Mesejo, Xavier Alameda-Pineda, Radu Horaud
Deep learning revolutionized data science, and recently its popularity has grown exponentially, as did the amount of papers employing deep networks.
no code implementations • 18 Nov 2017 • Stéphane Lathuilière, Benoit Massé, Pablo Mesejo, Radu Horaud
Our approach enables a robot to learn and to adapt its gaze control strategy for human-robot interaction neither with the use of external sensors nor with human supervision.
no code implementations • 5 Oct 2017 • Richard T. Marriott, Alexander Paschevich, Radu Horaud
We propose a novel algorithm for unsupervised extraction of piecewise planar models from depth-data.
no code implementations • CVPR 2017 • Stephane Lathuiliere, Remi Juge, Pablo Mesejo, Rafael Munoz-Salinas, Radu Horaud
In this particular problem, we show that inverse regression outperforms regression models currently used by state-of-the-art computer vision methods.
no code implementations • 14 Mar 2017 • Benoît Massé, Silèye Ba, Radu Horaud
The visual focus of attention (VFOA) has been recognized as a prominent conversational cue.
no code implementations • 6 Sep 2016 • Georgios Evangelidis, Radu Horaud
Solutions to this problem are often approximated by repeatedly solving for pairwise registration, which results in an uneven treatment of the sets forming a pair: a model set and a data set.
no code implementations • 31 Mar 2016 • Vincent Drouard, Radu Horaud, Antoine Deleforge, Silèye Ba, Georgios Evangelidis
Head-pose estimation has many applications, such as social event analysis, human-robot and human-computer interaction, driving assistance, and so forth.
no code implementations • 31 Mar 2016 • Israel D. Gebru, Silèye Ba, Xiaofei Li, Radu Horaud
An audio-visual spatiotemporal diarization model is proposed.
no code implementations • 4 Sep 2015 • Israel D. Gebru, Xavier Alameda-Pineda, Florence Forbes, Radu Horaud
We propose a model selection method based on a minimum message length criterion, provide a weight initialization strategy, and validate the proposed algorithms by comparing them with several state of the art parametric and non-parametric clustering techniques.
no code implementations • 4 Sep 2015 • Sileye . Ba, Xavier Alameda-Pineda, Alessio Xompero, Radu Horaud
In this paper, we propose an on-line variational Bayesian model for multi-person tracking from cluttered visual observations provided by person detectors.
no code implementations • 30 Sep 2014 • Antoine Deleforge, Florence Forbes, Sileye . Ba, Radu Horaud
This involves resolving inverse problems which can be addressed within machine learning, with the advantage that, once a relationship between physical parameters and spectra has been established in a data-driven fashion, the learned relationship can be used to estimate physical parameters for new hyper-spectral observations.
no code implementations • 2014 22nd International Conference on Pattern Recognition 2014 • Georgios Evangelidis, Gurkirt Singh, Radu Horaud
Further, the use of a Fisher kernel representation is suggested to describe the skeletal quads contained in a (sub)action.
Ranked #120 on Skeleton Based Action Recognition on NTU RGB+D
no code implementations • 12 Aug 2014 • Antoine Deleforge, Radu Horaud, Yoav Schechner, Laurent Girin
Indeed, we demonstrate that the method can be used for audio-visual fusion, namely to map speech signals onto images and hence to spatially align the audio and visual modalities, thus enabling to discriminate between speaking and non-speaking faces.
no code implementations • 2 Jun 2014 • Kaustubh Kulkarni, Georgios Evangelidis, Jan Cech, Radu Horaud
Continuous action recognition is more challenging than isolated recognition because classification and segmentation must be simultaneously carried out.
no code implementations • 26 May 2014 • Fabio Cuzzolin, Diana Mateus, Radu Horaud
In an unsupervised context, i. e., no prior model of the moving object(s) is available, such a structure has to be learned from the data in a bottom-up fashion.
no code implementations • 31 Jan 2014 • Miles Hansard, Georgios Evangelidis, Quentin Pelorson, Radu Horaud
It is desirable to merge the depth and colour information, in order to obtain a coherent scene representation.
no code implementations • 24 Jan 2014 • Miles Hansard, Radu Horaud, Michel Amat, Georgios Evangelidis
It is convenient to calibrate time-of-flight cameras by established methods, using images of a chequerboard pattern.
no code implementations • 6 Nov 2013 • Xavier Alameda-Pineda, Radu Horaud
Natural human-robot interaction in complex and unpredictable environments is one of the main research lines in robotics.
no code implementations • 10 Aug 2013 • Antoine Deleforge, Florence Forbes, Radu Horaud
We introduce a mixture of locally-linear probabilistic mapping model that starts with estimating the parameters of inverse regression, and follows with inferring closed-form solutions for the forward parameters of the high-dimensional regression problem of interest.